Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10477
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize important points or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "it should be" / "it is" + verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    it should be noted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.83
    Portale
    -0.73
    dafx
    -0.64
    ----</
    -0.64
     VIAF
    -0.61
     estekak
    -0.61
     Wikimedijinoj
    -0.61
    ServletException
    -0.60
    WebVitals
    -0.60
    发表于
    -0.59
    POSITIVE LOGITS
     note
    3.60
     Note
    3.02
    note
    2.95
    Note
    2.79
     notes
    2.61
     noted
    2.42
     NOTE
    2.41
     noting
    2.23
     Notes
    2.19
    NOTE
    2.17
    Activations Density 0.540%

    No Known Activations